Contextualized Item Reminder Assitance

1. A method for reminding at least one user about one or more items related to an upcoming event, the method comprising: training a computerized item machine learning system to determine a likelihood that the at least one user will forget an item on a list of items based on information from an item profile store; training a computerized conversational machine learning system to determine a conversation trigger signal based on attributes of the items, the attributes comprising sensitivity, characteristics and context; determining, using the computerized item machine learning system, an aspect of context-sensitive implications associated with a forgotten item on the list of items; determining, using the computerized item machine learning system, a degree of item importance based on the context-sensitive implications using a semantics-based technique; identifying, using a computerized event machine learning system, the upcoming event based on user data and an event context builder model; obtaining context for determining the list of items useful for the upcoming event; determining, using the context and stored historical user data, the list of items for the identified upcoming event using the learned likelihoods, the determined degree of item importance, and by learning item to item association using historical observations from past events and by analyzing the upcoming event, the obtained context, and a user profile using the computerized item machine learning system; determining item reminder enhancement factors in response to the upcoming event and the determined list of items; determining content selection models based on the context, the user data, and the item reminder enhancement factors; generating conversational content, using the computerized conversational machine learning system, for engaging the at least one user by obtaining an item set <I> and user data <U>; training a set of conversational content generation models based on the item set <I>, the user data <U>, and an analysis of other contextual data; generating potential conversational content by applying the set of conversational content generation models; and applying the content selection models to the potential conversational content; determining, using the computerized conversational machine learning system, the conversation trigger signal based on contextual information related to the conversational content and an analysis of user feedback, wherein the determining of the conversation trigger signal is performed based on sensing the user using a proximity sensor; and presenting the conversational content to the user via a computing device in response to receiving the conversation trigger signal.

2. The method of claim 1 , wherein the determining the list of items further comprises receiving an identity of one or more items from a plurality of sources based on one or more of a signal sent from an item, a list of items generated by a system by using predictive models, a user-supplied list of items, and one or more items detected during conversation.

3. The method of claim 1 , wherein the determining the conversation trigger signal is performed based on one or more of detecting a user interaction with a specified computing device, sensing the user based on proximity to a geo-fence region, detecting an expiration of a time trigger, receiving text based on voice recognition, and analyzing attributes of an item on the list of items.

4. The method of claim 1 , wherein the determining the conversation trigger signal further comprises detecting the conversation trigger signal based on one or more of a user speaking to a voice-controlled device, a user-specified trigger event, and a real-time instrumentation of user interaction.

5. The method of claim 1 , wherein the determining the conversation trigger signal further comprises determining context regarding when to auto-trigger a conversation based on conversation sensitivity and appropriateness.

6. The method of claim 1 , further comprising establishing at least one model to rank the potential conversational content according to attributes of the item on the list of items and the user data, wherein the conversational content and the potential conversational content is content designed to conduct a conversation with the at least one user.

7. The method of claim 1 , further comprising dynamic routing of one or more forgotten items based on an analysis of the degree of item importance.

8. The method of claim 1 , further comprising estimating a cost of forgetting at least one item on the list of items.

9. The method of claim 1 , wherein the identifying the upcoming event further comprises employing a machine learning algorithm using a plurality of data points, the plurality of data points comprising one or more of calendar information, a message, an email, and a conversation.

10. The method of claim 1 , wherein the user data comprises: the user profile, the user profile comprising data obtained from a user's calendar, an email, and a user device; and one or more of a profile of items historically carried by a user, a preference for time and modality of reminder, a user's response to a reminder, historical user travel information, historical user calendar information, historical user behavioral data, a previous history of implications or risks due to forgotten items, and historical user interactions with a user device.

11. The method of claim 1 , wherein the identifying the upcoming event further comprises obtaining a first set of user data; and predicting, using the computerized item machine learning system, at least one item selection factor based on the identified upcoming event and the first set of user data, wherein the identification of the upcoming event is based on associated contextual information in the first set of user data.

12. The method of claim 11 , wherein the at least one item selection factor is a degree of forgetting an item, an importance level, a priority level, a sensitivity, a first context, and an affinity measure.

13. The method of claim 11 , wherein the list of items is determined based on the predicted item selection factors and the first set of user data.

14. The method of claim 11 , wherein the first set of user data comprises one or more of historical user travel information, user calendar history, historical user behavioral data, a previous history of implications or risks due to a forgotten item, a user profile, and historical interactions with a user device.

15. The method of claim 1 , further comprising determining an amelioration action, the amelioration action being one or more of dynamically triggering a routing of a forgotten item, identifying a replacement item, identifying an individual to transport the forgotten item, and arranging transportation and delivery options by a courier for the forgotten item.

16. The method of claim 1 , wherein the determining the conversation trigger signal further comprises performing computerized voice recognition to determine text indicative of the conversation trigger signal.

17. A computer implementing a machine learning system, said computer comprising: a memory; and at least one processor, coupled to said memory, and operative to perform operations comprising: training a computerized item machine learning system to determine a likelihood that at least one user will forget an item on a list of items based on information from an item profile store; training the computerized item machine learning system to determine a conversation trigger signal based on attributes of the items, the attributes comprising sensitivity, characteristics and context; determining, using the computerized item machine learning system, an aspect of context-sensitive implications associated with a forgotten item on the list of items; determining, using the computerized item machine learning system, a degree of item importance based on the context-sensitive implications using a semantics-based technique; identifying, using a computerized event machine learning system, the upcoming event based on user data and an event context builder model; obtaining context for determining the list of items useful for the upcoming event; determining, using the context and stored historical user data, the list of items for the identified upcoming event using the likelihoods, the determined degree of item importance, and by learning item to item association using historical observations from past events and by analyzing the upcoming event, the obtained context, and a user profile using the computerized item machine learning system; determining item reminder enhancement factors in response to the upcoming event and the determined list of items; determining content selection models based on the context, the user data, and the item reminder enhancement factors; generating conversational content, using the computerized conversational machine learning system, for engaging the at least one user by obtaining an item set <I> and user data <U>; training a set of conversational content generation models based on the item set <I>, the user data <U>, and an analysis of other contextual data; generating potential conversational content by applying the set of conversational content generation models; and applying the content selection models to the potential conversational content; determining, using the computerized conversational machine learning system, the conversation trigger signal based on contextual information related to the conversational content and an analysis of user feedback, wherein the determining of the conversation trigger signal is performed based on sensing the user using a proximity sensor; and presenting the conversational content to the user via a computing device in response to receiving the conversation trigger signal.

18. A non-transitory computer readable medium comprising computer executable instructions which when executed by a computer cause the computer to perform the method of: training a computerized item machine learning system to determine a likelihood that at least one user will forget an item on a list of items based on information from an item profile store; training the computerized item machine learning system to determine a conversation trigger signal based on attributes of the items, the attributes comprising sensitivity, characteristics and context; determining, using the computerized item machine learning system, an aspect of context-sensitive implications associated with a forgotten item on the list of items; determining, using the computerized item machine learning system, a degree of item importance based on the context-sensitive implications using a semantics-based technique; identifying, using a computerized event machine learning system, the upcoming event based on user data and an event context builder model; obtaining context for determining the list of items useful for the upcoming event; determining, using the context and stored historical user data, the list of items for the identified upcoming event using the learned likelihoods, the determined degree of item importance, and by learning item to item association using historical observations from past events and by analyzing the upcoming event, the obtained context, and a user profile using the computerized item machine learning system; determining item reminder enhancement factors in response to the upcoming event and the determined list of items; determining content selection models based on the context, the user data, and the item reminder enhancement factors; generating conversational content, using the computerized conversational machine learning system, for engaging the at least one user by obtaining an item set <I> and user data <U>; training a set of conversational content generation models based on the item set <I>, the user data <U>, and an analysis of other contextual data; generating potential conversational content by applying the set of conversational content generation models; and applying the content selection models to the potential conversational content; determining, using the computerized conversational machine learning system, the conversation trigger signal based on contextual information related to the conversational content and an analysis of user feedback, wherein the determining of the conversation trigger signal is performed based on sensing the user using a proximity sensor; and presenting the conversational content to the user via a computing device in response to receiving the conversation trigger signal.